Failed to load the checkpoint file provided in the google drive.

[Irlyue]

The repo has already provided a latest_net_G.pth in the folder ./checkpoints/experiment_name. However, as I go through the readme file and download the checkpoint file from the google drive, I cannot load it into the resnet_9blocks generator. It got some unexpected keys in the state_dict:

    Unexpected key(s) in state_dict: "model.10.conv_block.6.weight", "model.10.conv_block.6.bias", "model.10.conv_block.7.running_mean", "model.10.conv_block.7.running_var", "model.11.conv_block.6.weight", "model.11.conv_block.6.bias", "model.11.conv_block.7.running_mean", "model.11.conv_block.7.running_var", "model.12.conv_block.6.weight", "model.12.conv_block.6.bias", "model.12.conv_block.7.running_mean", "model.12.conv_block.7.running_var", "model.13.conv_block.6.weight", "model.13.conv_block.6.bias", "model.13.conv_block.7.running_mean", "model.13.conv_block.7.running_var", "model.14.conv_block.6.weight", "model.14.conv_block.6.bias", "model.14.conv_block.7.running_mean", "model.14.conv_block.7.running_var", "model.15.conv_block.6.weight", "model.15.conv_block.6.bias", "model.15.conv_block.7.running_mean", "model.15.conv_block.7.running_var", "model.16.conv_block.6.weight", "model.16.conv_block.6.bias", "model.16.conv_block.7.running_mean", "model.16.conv_block.7.running_var", "model.17.conv_block.6.weight", "model.17.conv_block.6.bias", "model.17.conv_block.7.running_mean", "model.17.conv_block.7.running_var", "model.18.conv_block.6.weight", "model.18.conv_block.6.bias", "model.18.conv_block.7.running_mean", "model.18.conv_block.7.running_var".

Could it be the version problem of Pytorch? (Mine is 0.4.1)

[ak9250]

getting same problem

[Jambalaya11]

+1

[QWERDF007]

+1 when PyTorch version is 1.0

[furuit]

+1

[qingsenyangit]

+1

[SeaOfOcean]

+1

[kregmi]

+1

[MrBurnst]

+1

[Madrid-Ista]

+1

[Jarvisss]

any solutions?

[doduythao]

so do I

[Muzammal-Naseer]

+1

[umar1992]

I am facing the same issue..my Pytorch version is 1.0.1. Anyone could find any solution?

[leandepk]

have solution？？？

[96lives]

It seems like one commit changed the architecture of ResNet! Erase (repo root)/models/networks.py line 219 ~ 230 and add

if use_dropout:
    blocks += [nn.Dropout(0.5)]
blocks += padAndConv[padding_type] + [norm_layer(dim)]

to make the code work.

However, I couldn't get the unblurry result with the pretrained model running....

[idealboy]

＋１